Sciweavers

2711 search results - page 1 / 543
» Convergence of the Wake-Sleep Algorithm
Sort
View
NIPS
1998
13 years 6 months ago
Convergence of the Wake-Sleep Algorithm
The W-S (Wake-Sleep) algorithm is a simple learning rule for the models with hidden variables. It is shown that this algorithm can be applied to a factor analysis model which is a...
Shiro Ikeda, Shun-ichi Amari, Hiroyuki Nakahara
CDC
2010
IEEE
196views Control Systems» more  CDC 2010»
12 years 11 months ago
Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
Vladislav B. Tadic
CEC
2007
IEEE
13 years 11 months ago
Convergence and rate of convergence of a foraging ant model
— We present an ant model that solves a discrete foraging problem. We describe simulations and provide a complete convergence analysis: we show that the ant population computes t...
Amine M. Boumaza, Bruno Scherrer
ATAL
2007
Springer
13 years 11 months ago
Convergence and rate of convergence of a simple ant model
We present a simple ant model that solves a discrete foraging problem. We describe simulations and provide a complete convergence analysis: we show that the ant population compute...
Amine M. Boumaza, Bruno Scherrer